diyjac / sdc-p5 Goto Github PK

Hi,
for "python3 P5pipeline.py test_image/test1.jpg output_image/test1.jpg"
it is successful.

but for "python3 P5pipeline.py test_video/test1.mp4 output_video/test1.mp4"

Camera Calibration data restored from camera_cal/calibrationdata.p
video processing test_video/test1.mp4...
Traceback (most recent call last):
File "P5pipeline.py", line 238, in
video_clip = clip1.fl_image(process_image)
File "/usr/local/lib/python3.5/dist-packages/moviepy/video/VideoClip.py", line 514, in fl_image
return self.fl(lambda gf, t: image_func(gf(t)), apply_to)
File "/usr/local/lib/python3.5/dist-packages/moviepy/Clip.py", line 137, in fl
newclip = self.set_make_frame(lambda t: fun(self.get_frame, t))
File "", line 2, in set_make_frame
File "/usr/local/lib/python3.5/dist-packages/moviepy/decorators.py", line 14, in outplace
f(newclip, *a, **k)
File "/usr/local/lib/python3.5/dist-packages/moviepy/video/VideoClip.py", line 669, in set_make_frame
self.size = self.get_frame(0).shape[:2][::-1]
File "", line 2, in get_frame
File "/usr/local/lib/python3.5/dist-packages/moviepy/decorators.py", line 89, in wrapper
return f(*new_a, **new_kw)
File "/usr/local/lib/python3.5/dist-packages/moviepy/Clip.py", line 94, in get_frame
return self.make_frame(t)
File "/usr/local/lib/python3.5/dist-packages/moviepy/Clip.py", line 137, in
newclip = self.set_make_frame(lambda t: fun(self.get_frame, t))
File "/usr/local/lib/python3.5/dist-packages/moviepy/video/VideoClip.py", line 514, in
return self.fl(lambda gf, t: image_func(gf(t)), apply_to)
File "P5pipeline.py", line 115, in process_image
image, roadMgr, diagMgr, scrType=scrType, debug=debug, resized=resized)
File "P5pipeline.py", line 63, in process_road_image
roadMgr.findLanes(img, resized=resized)
File "/home/cetc28/Program/SDC-P5-master/p5lib/roadManager.py", line 361, in findLanes
self.addLaneLeft(curLane)
File "/home/cetc28/Program/SDC-P5-master/p5lib/roadManager.py", line 172, in addLaneLeft
self.curImgFtr, curLane, faint=faint, resized=self.resized)
File "/home/cetc28/Program/SDC-P5-master/p5lib/line.py", line 102, in createPolyFitLeft
rightLane.lines[rightLane.right].currentFit)
File "/usr/local/lib/python3.5/dist-packages/numpy/lib/polynomial.py", line 778, in polysub
val = a1 - a2
TypeError: unsupported operand type(s) for -: 'NoneType' and 'NoneType'

Tank you!

Hi John! Thanks for making this project available.
I would like to mention there is a missing dependency webcolor for visualize those cool effect.
after activating conda environment (source activate carnd-term1)
should conda install -c conda-forge webcolors=1.7
that's it! And I have fun, thank you!

when I use this command python3 P5pipeline.py test_images/test1.jpg output_images/test1.jpg i get

Camera Calibration data restored from camera_cal/calibrationdata.p
image processing test_images/test1.jpg...
Traceback (most recent call last):
  File "P5pipeline.py", line 229, in <module>
    imageout = process_image(image)
  File "P5pipeline.py", line 115, in process_image
    image, roadMgr, diagMgr, scrType=scrType, debug=debug, resized=resized)
  File "P5pipeline.py", line 63, in process_road_image
    roadMgr.findLanes(img, resized=resized)
  File "/media/bignrz/World/projects/self driving car/SDC-P5/p5lib/roadManager.py", line 493, in findLanes
    self.vehicleScan, self.roadGrid)
  File "/media/bignrz/World/projects/self driving car/SDC-P5/p5lib/vehicleDetection.py", line 321, in detectVehicles
    hist_bins=32, hist_range=(0, 256))
  File "/media/bignrz/World/projects/self driving car/SDC-P5/p5lib/vehicleDetection.py", line 159, in extract_features
    cell_per_block, vis=False, feature_vec=True)
  File "/media/bignrz/World/projects/self driving car/SDC-P5/p5lib/vehicleDetection.py", line 99, in get_hog_features
    feature_vector=feature_vec)
TypeError: hog() got an unexpected keyword argument 'visualise'

and when using python3 P5pipeline.py v.mp4 v_out.mp4 (the same as #4) I get

Camera Calibration data restored from camera_cal/calibrationdata.p
video processing v.mp4...
Traceback (most recent call last):
  File "P5pipeline.py", line 238, in <module>
    video_clip = clip1.fl_image(process_image)
  File "/home/bignrz/.local/lib/python3.7/site-packages/moviepy/video/VideoClip.py", line 490, in fl_image
    return self.fl(lambda gf, t: image_func(gf(t)), apply_to)
  File "/home/bignrz/.local/lib/python3.7/site-packages/moviepy/Clip.py", line 136, in fl
    newclip = self.set_make_frame(lambda t: fun(self.get_frame, t))
  File "</home/bignrz/anaconda3/lib/python3.7/site-packages/decorator.py:decorator-gen-61>", line 2, in set_make_frame
  File "/home/bignrz/.local/lib/python3.7/site-packages/moviepy/decorators.py", line 14, in outplace
    f(newclip, *a, **k)
  File "/home/bignrz/.local/lib/python3.7/site-packages/moviepy/video/VideoClip.py", line 644, in set_make_frame
    self.size = self.get_frame(0).shape[:2][::-1]
  File "</home/bignrz/anaconda3/lib/python3.7/site-packages/decorator.py:decorator-gen-11>", line 2, in get_frame
  File "/home/bignrz/.local/lib/python3.7/site-packages/moviepy/decorators.py", line 89, in wrapper
    return f(*new_a, **new_kw)
  File "/home/bignrz/.local/lib/python3.7/site-packages/moviepy/Clip.py", line 93, in get_frame
    return self.make_frame(t)
  File "/home/bignrz/.local/lib/python3.7/site-packages/moviepy/Clip.py", line 136, in <lambda>
    newclip = self.set_make_frame(lambda t: fun(self.get_frame, t))
  File "/home/bignrz/.local/lib/python3.7/site-packages/moviepy/video/VideoClip.py", line 490, in <lambda>
    return self.fl(lambda gf, t: image_func(gf(t)), apply_to)
  File "P5pipeline.py", line 115, in process_image
    image, roadMgr, diagMgr, scrType=scrType, debug=debug, resized=resized)
  File "P5pipeline.py", line 63, in process_road_image
    roadMgr.findLanes(img, resized=resized)
  File "/media/bignrz/World/projects/self driving car/SDC-P5/p5lib/roadManager.py", line 361, in findLanes
    self.addLaneLeft(curLane)
  File "/media/bignrz/World/projects/self driving car/SDC-P5/p5lib/roadManager.py", line 172, in addLaneLeft
    self.curImgFtr, curLane, faint=faint, resized=self.resized)
  File "/media/bignrz/World/projects/self driving car/SDC-P5/p5lib/line.py", line 102, in createPolyFitLeft
    rightLane.lines[rightLane.right].currentFit)
  File "<__array_function__ internals>", line 6, in polysub
  File "/home/bignrz/anaconda3/lib/python3.7/site-packages/numpy/lib/polynomial.py", line 842, in polysub
    val = a1 - a2
TypeError: unsupported operand type(s) for -: 'NoneType' and 'NoneType'

I tried on both python3.7, python 3.6 and python3.5 and do not know what is the problem

Hi. thank you for sharing this valuable information. I m now completing opencv cources. and I found this great work. actually I want to create a small gadget for my car with Raspberry pi. I want to modify your code that uses live camera and shows processed cameare video on the screen. I examined your codes but could not get opinion where to modify to accomplish my idea. any clue could you provide me. best regards.

It is giving error:

1. ImportError: cannot import name 'joblib' from 'sklearn.externals' (/usr/local/lib/python3.7/dist-packages/sklearn/externals/__init__.py)

Fix,
In pylib/vehicleDetection.py change to import joblib

2. FileNotFoundError: [Errno 2] No such file or directory: './trained/CHOGRGB4.pkl'

Colab Link:
https://colab.research.google.com/drive/1TGWisevUpECP7hOOzca8fA1o9dlyWj29?usp=sharing

Hi,
python3 P5pipeline.py test_images/test1.jpg output_images/test1.jpg

Camera Calibration data restored from camera_cal/calibrationdata.p
Traceback (most recent call last):
File "P5pipeline.py", line 218, in
roadMgr = RoadManager(camCal, debug=debug, scrType=scrType)
File "/mnt/hgfs/study/123/Vehicle-Detection/SDC-P5/p5lib/roadManager.py", line 130, in init
self.threshold)
File "/mnt/hgfs/study/123/Vehicle-Detection/SDC-P5/p5lib/vehicleDetection.py", line 44, in init
self.svc = joblib.load(self.trained_model)
File "/usr/local/lib/python3.5/dist-packages/sklearn/externals/joblib/numpy_pickle.py", line 570, in load
with open(filename, 'rb') as f:
NotADirectoryError: [Errno 20] Not a directory: './trained/CHOGRGB4.pkl'
Tank you!